布隆過濾器（Bloom Filter）的java實現

Hash Function:

雜湊函式就是將任意長度的資料轉變成固定長度的資料（http://en.wikipedia.org/wiki/Hash_function）

Bloom Filter:

用java實現的Bloom Filter的程式碼如下

import java.util.BitSet;

public class BloomFilter {
	private static final int DEFAULT_SIZE = 2 << 24;	// Set DEFAULT_SIZE as 2^24 
	private static final int[] seed = new int[] {
		5, 7, 11, 13, 31, 37, 61
	};
	private BitSet bits = new BitSet(DEFAULT_SIZE);
	private SimpleHash[] func = new SimpleHash[seed.length];
	
	public BloomFilter() {
		for (int i = 0; i < seed.length; i++) {
			func[i] = new SimpleHash(DEFAULT_SIZE, seed[i]);
		}
	}

	public void add(String value) {
		for (SimpleHash f : func) 
			bits.set(f.hash(value), true);
	}

	public boolean contains(String value) {
		if (value == null) 
			return false;
		boolean rslt = true;
		for (SimpleHash f : func) {
			rslt = rslt & bits.get(f.hash(value));
		}
		return rslt;
	}

	public static class SimpleHash{
		private int cap;
		private int seed;

		SimpleHash(int cap, int seed){
			this.cap = cap;
			this.seed = seed;
		}

		public int hash(String value){
			int result = 0;
			int len = value.length();
			for (int i = 0; i < len; i++)
				result = result * seed + value.charAt(i);
			return (cap -1) & result;
		}
	}
}

測試程式程式碼如下：

public class TestBloomFilter{
	public static void main(String[] args) {
		BloomFilter bf =new BloomFilter();
		bf.add("www.baidu.com");
		bf.add("www.sohu.com");
		bf.add("www.163.com");
		if(bf.contains("www.cctv.com"))
			System.out.println("www.cctv.com is in the set");
		else
			System.out.println("www.cctv.com is not in the set");

		if(bf.contains("www.baidu.com"))
			System.out.println("www.baidu.com is in the set");
		else
			System.out.println("www.baidu.com is not in the set");
	}
}